Search Results for author:
Found 46 papers, 25 papers with code
A Learning Paradigm for Interpretable Gradients
This paper studies interpretability of convolutional networks by means of saliency maps.
CA-Stream: Attention-based pooling for interpretable image recognition
Explanations obtained from transformer-based architectures in the form of raw attention, can be seen as a class-agnostic saliency map.
On Train-Test Class Overlap and Detection for Image Retrieval
How important is it for training and evaluation sets to not have class overlap in image retrieval?
PowMix: A Versatile Regularizer for Multimodal Sentiment Analysis
Multimodal sentiment analysis (MSA) leverages heterogeneous data sources to interpret the complex nature of human sentiments.
Adaptive Anchor Label Propagation for Transductive Few-Shot Learning
Our novel algorithm, Adaptive Anchor Label Propagation}, outperforms the standard label propagation algorithm by as much as 7% and 2% in the 1-shot and 5-shot settings respectively.
Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video
But are we making the best use of data?
Zero-Shot and Few-Shot Video Question Answering with Multi-Modal Prompts
Recent vision-language models are driven by large-scale pretrained models.
Few-shot Video Question Answering
Zero-Shot Video Question Answer
Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?
By discussing the properties of each group of methods, we derive SimPool, a simple attention-based pooling mechanism as a replacement of the default one for both convolutional and transformer encoders.
Adaptive manifold for imbalanced transductive few-shot learning
Our method exploits the underlying manifold of the labeled support examples and unlabeled queries by using manifold similarity to predict the class probability distribution per query.
PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervision
Evaluations on various ShapeNet categories demonstrate the ability of our model to generate editable 3D objects of improved fidelity, compared to previous part-based generative approaches that require 3D supervision or models relying on NeRFs.
Opti-CAM: Optimizing saliency maps for interpretability
Methods based on class activation maps (CAM) provide a simple mechanism to interpret predictions of convolutional neural networks by using linear combinations of feature maps as saliency maps.
Generating Part-Aware Editable 3D Shapes Without 3D Supervision
Evaluations on various ShapeNet categories demonstrate the ability of our model to generate editable 3D objects of improved fidelity, compared to previous part-based generative approaches that require 3D supervision or models relying on NeRFs.
Boosting vision transformers for image retrieval
(4) We enhance locality of interactions at the deeper layers of the encoder, which is the relative weakness of vision transformers.
Teach me how to Interpolate a Myriad of Embeddings
Finally, to address inconsistencies due to linear target interpolation, we introduce a self-distillation approach to generate and interpolate synthetic targets.
What to Hide from Your Students: Attention-Guided Masked Image Modeling
In this work, we argue that image token masking differs from token masking in text, due to the amount and correlation of tokens in an image.
AlignMix: Improving representations by interpolating aligned features
Mixup is a powerful data augmentation method that interpolates between two or more examples in the input or feature space and between the corresponding target labels.
All the attention you need: Global-local, spatial-channel attention for image retrieval
Apart from backbone, training pipelines and loss functions, popular approaches have focused on different spatial pooling and attention mechanisms, which are at the core of learning a powerful global image representation.
Tensor feature hallucination for few-shot learning
We follow a different approach and investigate how a simple and straightforward synthetic data generation method can be used effectively.
It Takes Two to Tango: Mixup for Deep Metric Learning
In this work, we aim to bridge this gap and improve representations using mixup, which is a powerful data augmentation approach interpolating two or more examples and corresponding target labels at a time.
Ranked #8 on
Metric Learning
on CUB-200-2011
(using extra training data)
Few-shot learning via tensor hallucination
Few-shot classification addresses the challenge of classifying examples given only limited labeled data.
AlignMixup: Improving Representations By Interpolating Aligned Features
Mixup is a powerful data augmentation method that interpolates between two or more examples in the input or feature space and between the corresponding target labels.
Ranked #1 on
Representation Learning
on CIFAR10
On the hidden treasure of dialog in video question answering
High-level understanding of stories in video such as movies and TV shows from raw data is extremely challenging.
Ranked #1 on
Video Question Answering
on KnowIT VQA
Local Propagation for Few-Shot Learning
The challenge in few-shot learning is that available data is not enough to capture the underlying distribution.
Iterative label cleaning for transductive and semi-supervised few-shot learning
Few-shot learning amounts to learning representations and acquiring knowledge such that novel tasks may be solved with both supervision and data being limited.
Asymmetric metric learning for knowledge transfer
This acts as a simple combination of knowledge transfer with the original metric learning task.
Few-Shot Few-Shot Learning and the role of Spatial Attention
This motivates us to study a problem where the representation is obtained from a classifier pre-trained on a large-scale dataset of a different domain, assuming no access to its training process, while the base class data are limited to few examples per class and their role is to adapt the representation to the domain at hand rather than learn from scratch.
Walking on the Edge: Fast, Low-Distortion Adversarial Examples
Adversarial examples of deep neural networks are receiving ever increasing attention because they help in understanding and reducing the sensitivity to their input.
Training Object Detectors from Few Weakly-Labeled and Many Unlabeled Images
Weakly-supervised object detection attempts to limit the amount of supervision by dispensing the need for bounding boxes, but still assumes image-level labels on the entire training set.
Ranked #23 on
Weakly Supervised Object Detection
on PASCAL VOC 2012 test
(using extra training data)
Rethinking deep active learning: Using unlabeled data at model training
By systematically evaluating on a number of popular acquisition strategies and datasets, we find that the use of unlabeled data during model training brings a surprising accuracy improvement in image classification, compared to the differences between acquisition strategies.
Graph convolutional networks for learning with few clean and many noisy labels
In this work we consider the problem of learning a classifier from noisy labels when a few clean labeled examples are given.
Local Features and Visual Words Emerge in Activations
We propose a novel method of deep spatial matching (DSM) for image retrieval.
Label Propagation for Deep Semi-supervised Learning
In this work, we employ a transductive label propagation method that is based on the manifold assumption to make predictions on the entire dataset and use these predictions to generate pseudo-labels for the unlabeled data and train a deep neural network.
Dense Classification and Implanting for Few-Shot Learning
Training deep neural networks from few examples is a highly challenging and key problem for many computer vision tasks.
Hybrid Diffusion: Spectral-Temporal Graph Filtering for Manifold Ranking
State of the art image retrieval performance is achieved with CNN features and manifold ranking using a k-NN similarity graph that is pre-computed off-line.
Mining on Manifolds: Metric Learning without Labels
Positive examples are distant points on a single manifold, while negative examples are nearby points on different manifolds.
Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking
In particular, annotation errors, the size of the dataset, and the level of challenge are addressed: new annotation for both datasets is created with an extra attention to the reliability of the ground truth.
Unsupervised object discovery for instance recognition
Eliminating the impact of the clutter on the image descriptor increases the chance of retrieving relevant images and prevents topic drift due to actually retrieving the clutter in the case of query expansion.
Panorama to panorama matching for location recognition
Location recognition is commonly treated as visual instance retrieval on "street view" imagery.
Unsupervised part learning for visual recognition
This strategy opens the door to the use of PBM in new applications for which the notion of image categories is irrelevant, such as instance-based image retrieval, for example.
Fast Spectral Ranking for Similarity Search
This makes the Euclidean nearest neighbor search biased for this task.
Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations
The diffusion is carried out on descriptors of overlapping image regions rather than on a global image descriptor like in previous approaches.
Automatic discovery of discriminative parts as a quadratic assignment problem
Part-based image classification consists in representing categories by small sets of discriminative parts upon which a representation of the images is built.
Web-Scale Image Clustering Revisited
Large scale duplicate detection, clustering and mining of documents or images has been conventionally treated with seed detection via hashing, followed by seed growing heuristics using fast search.
Early Burst Detection for Memory-Efficient Image Retrieval
Then, we show the interest of using this strategy in an asymmetrical manner, with only the database features being aggregated but not those of the query.
Locally Optimized Product Quantization for Approximate Nearest Neighbor Search
We present a simple vector quantizer that combines low distortion with fast search and apply it to approximate nearest neighbor (ANN) search in high dimensional spaces.
