Search Results for author:
Found 46 papers, 37 papers with code
Translate-Train Embracing Translationese Artifacts
Translate-train is a general training approach to multilingual tasks.
Freestyle Layout-to-Image Synthesis
In this work, we explore the freestyle capability of the model, i. e., how far can it generate unseen semantics (e. g., classes, attributes, and styles) onto a given layout, and call the task Freestyle LIS (FLIS).
Class-Incremental Exemplar Compression for Class-Incremental Learning
Exemplar-based class-incremental learning (CIL) finetunes the model with all samples of new classes but few-shot exemplars of old classes in each incremental phase, where the "few-shot" abides by the limited memory budget.
Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection
At each MIL training iteration, we use the current detector to divide the samples into two groups with different context biases: the most confident abnormal/normal snippets and the rest ambiguous ones.
Extracting Class Activation Maps from Non-Discriminative Features as well
Extracting class activation maps (CAM) from a classification model often results in poor coverage on foreground objects, i. e., only the discriminative region (e. g., the "head" of "sheep") is recognized and the rest (e. g., the "leg" of "sheep") mistakenly as background.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Semantic Scene Completion with Cleaner Self
SSC is a well-known ill-posed problem as the prediction model has to "imagine" what is behind the visible surface, which is usually represented by Truncated Signed Distance Function (TSDF).
Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection
Without bells and whistles, our RePro achieves a new state-of-the-art performance on two VidVRD benchmarks of not only the base training object and predicate categories, but also the unseen ones.
RMM: Reinforced Memory Management for Class-Incremental Learning
Class-Incremental Learning (CIL) [40] trains classifiers under a strict memory budget: in each incremental phase, learning is done for new data, most of which is abandoned to free space for the next phase.
Online Hyperparameter Optimization for Class-Incremental Learning
Class-incremental learning (CIL) aims to train a classification model while the number of classes increases phase-by-phase.
Attention-based Class Activation Diffusion for Weakly-Supervised Semantic Segmentation
An intuitive solution is ``coupling'' the CAM with the long-range attention matrix of visual transformers (ViT) We find that the direct ``coupling'', e. g., pixel-wise multiplication of attention and activation, achieves a more global coverage (on the foreground), but unfortunately goes with a great increase of false positives, i. e., background pixels are mistakenly included.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Efficient Cross-Modal Video Retrieval with Meta-Optimized Frames
In turn, the frame-level optimization is through gradient descent using the meta loss of video retrieval model computed on the whole video.
Class Is Invariant to Context and Vice Versa: On Learning Invariance for Out-Of-Distribution Generalization
If the context in every class is evenly distributed, OOD would be trivial because the context can be easily removed due to an underlying principle: class is invariant to context.
On Mitigating Hard Clusters for Face Clustering
Face clustering is a promising way to scale up face recognition systems using large-scale unlabeled face images.
Equivariance and Invariance Inductive Bias for Learning from Insufficient Data
We are interested in learning robust models from insufficient data, without the need for any externally pre-trained checkpoints.
Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation
Specifically, due to the sum-over-class pooling nature of BCE, each pixel in CAM may be responsive to multiple classes co-occurring in the same receptive field.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Deconfounded Visual Grounding
We focus on the confounding bias between language and location in the visual grounding pipeline, where we find that the bias is the major visual reasoning bottleneck.
Self-Supervised Learning Disentangled Group Representation as Feature
A good visual representation is an inference map from observations (images) to features (vectors) that faithfully reflects the hidden modularized generative factors (semantics).
Wakening Past Concepts without Past Data: Class-incremental Learning from Placebos
However, we empirically observe that this both harms learning of new classes and also underperforms to distil old class knowledge from the previous phase model.
Attention-based Feature Aggregation
To implement this module, we define two variants of attention: self-attention on the summed-up feature map, and cross-attention between two feature maps before summed up.
Causal Attention for Unbiased Visual Recognition
Attention module does not always help deep models learn causal features that are robust in any confounding context, e. g., a foreground object feature is invariant to different backgrounds.
COSY: COunterfactual SYntax for Cross-Lingual Understanding
Pre-trained multilingual language models, e. g., multilingual-BERT, are widely used in cross-lingual tasks, yielding the state-of-the-art performance.
Transporting Causal Mechanisms for Unsupervised Domain Adaptation
However, the theoretical solution provided by transportability is far from practical for UDA, because it requires the stratification and representation of the unobserved confounder that is the cause of the domain gap.
A Large-Scale Benchmark for Food Image Segmentation
Existing food image segmentation models are underperforming due to two reasons: (1) there is a lack of high quality food image datasets with fine-grained ingredient labels and pixel-wise location masks -- the existing datasets either carry coarse ingredient labels or are small in size; and (2) the complex appearance of food makes it difficult to localize and recognize ingredients in food images, e. g., the ingredients may overlap one another in the same image, and the identical ingredient may appear distinctly in different food images.
Ranked #2 on
Semantic Segmentation
on FoodSeg103
(using extra training data)
Revisiting Local Descriptor for Improved Few-Shot Classification
Few-shot classification studies the problem of quickly adapting a deep learner to understanding novel classes based on few support images.
Counterfactual Zero-Shot and Open-Set Visual Recognition
We show that the key reason is that the generation is not Counterfactual Faithful, and thus we propose a faithful one, whose generation is from the sample-specific counterfactual question: What would the sample look like, if we set its class attribute to a certain class, while keeping its sample attribute unchanged?
Counterfactual Variable Control for Robust and Interpretable Question Answering
We then conduct two novel CVC inference methods (on trained models) to capture the effect of comprehensive reasoning as the final prediction.
Adaptive Aggregation Networks for Class-Incremental Learning
Class-Incremental Learning (CIL) aims to learn a classification model with the number of classes increasing phase-by-phase.
Interventional Few-Shot Learning
Specifically, we develop three effective IFSL algorithmic implementations based on the backdoor adjustment, which is essentially a causal intervention towards the SCM of many-shot learning: the upper-bound of FSL in a causal view.
Causal Intervention for Weakly-Supervised Semantic Segmentation
We present a causal inference framework to improve Weakly-Supervised Semantic Segmentation (WSSS).
Ranked #24 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
Feature Pyramid Transformer
Yet, the non-local spatial interactions are not across scales, and thus they fail to capture the non-local contexts of objects (or parts) residing in different scales.
Visual Commonsense R-CNN
We present a novel unsupervised feature representation learning method, Visual Commonsense Region-based Convolutional Neural Network (VC R-CNN), to serve as an improved visual region encoder for high-level tasks such as captioning and VQA.
Ranked #23 on
Image Captioning
on COCO Captions
Mnemonics Training: Multi-Class Incremental Learning without Forgetting
However, there is an inherent trade-off to effectively learning new concepts without catastrophic forgetting of previous ones.
Meta-Transfer Learning through Hard Tasks
In this paper, we propose a novel approach called meta-transfer learning (MTL) which learns to transfer the weights of a deep NN for few-shot learning tasks.
Joint Visual Grounding with Language Scene Graphs
In this paper, we alleviate the missing-annotation problem and enable the joint reasoning by leveraging the language scene graph which covers both labeled referent and unlabeled contexts (other objects, attributes, and relationships).
Learning to Self-Train for Semi-Supervised Few-Shot Classification
On each task, we train a few-shot model to predict pseudo labels for unlabeled data, and then iterate the self-training steps on labeled and pseudo-labeled data with each step followed by fine-tuning.
A Novel BiLevel Paradigm for Image-to-Image Translation
Image-to-image (I2I) translation is a pixel-level mapping that requires a large number of paired training data and often suffers from the problems of high diversity and strong category bias in image scenes.
An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning
"Empirical" means that the hyperparameters, e. g., used for learning and ensembling the epoch-wise models, are generated by hyperprior learners conditional on task-specific data.
Learning a Disentangled Embedding for Monocular 3D Shape Retrieval and Pose Estimation
We propose a novel approach to jointly perform 3D shape retrieval and pose estimation from monocular images. In order to make the method robust to real-world image variations, e. g. complex textures and backgrounds, we learn an embedding space from 3D data that only includes the relevant information, namely the shape and pose.
Meta-Transfer Learning for Few-Shot Learning
In this paper we propose a novel few-shot learning method called meta-transfer learning (MTL) which learns to adapt a deep NN for few shot learning tasks.
Self-Refining Deep Symmetry Enhanced Network for Rain Removal
Rain removal aims to extract and remove rain streaks from images.
A Hybrid Model for Identity Obfuscation by Face Replacement
As more and more personal photos are shared and tagged in social media, avoiding privacy risks such as unintended recognition becomes increasingly challenging.
Disentangled Person Image Generation
Generating novel, yet realistic, images of persons is a challenging task due to the complex interplay between the different image factors, such as the foreground, background and pose information.
Ranked #2 on
Gesture-to-Gesture Translation
on Senz3D
Natural and Effective Obfuscation by Head Inpainting
As more and more personal photos are shared online, being able to obfuscate identities in such photos is becoming a necessity for privacy protection.
Pose Guided Person Image Generation
This paper proposes the novel Pose Guided Person Generation Network (PG$^2$) that allows to synthesize person images in arbitrary poses, based on an image of that person and a novel pose.
Ranked #3 on
Gesture-to-Gesture Translation
on Senz3D
A Domain Based Approach to Social Relation Recognition
Social relations are the foundation of human daily life.
Orientation Driven Bag of Appearances for Person Re-identification
Experimental results on three public datasets and two proposed datasets demonstrate the superiority of the proposed approach, indicating the effectiveness of body structure and orientation information for improving re-identification performance.
