Search Results for author:
Found 48 papers, 24 papers with code
One Category One Prompt: Dataset Distillation using Diffusion Models
However, traditional dataset distillation approaches often struggle to scale effectively with high-resolution images and more complex architectures due to the limitations in bi-level optimization.
GeNIe: Generative Hard Negative Images Through Diffusion
To achieve this, inspired by recent diffusion based image editing techniques, we limit the number of diffusion iterations to ensure the generated image retains low-level and background features from the source image while representing the target category, resulting in a hard negative sample for the source category.
Compact3D: Compressing Gaussian Splat Radiance Field Models with Vector Quantization
3D Gaussian Splatting is a new method for modeling and rendering 3D radiance fields that achieves much faster learning and rendering time compared to SOTA NeRF methods.
BrainWash: A Poisoning Attack to Forget in Continual Learning
Continual learning has gained substantial attention within the deep learning community, offering promising solutions to the challenging problem of sequential learning.
NOLA: Networks as Linear Combination of Low Rank Random Basis
For instance, in larger models, even a rank one decomposition might exceed the number of parameters truly needed for adaptation.
SlowFormer: Universal Adversarial Patch for Attack on Compute and Energy Efficiency of Inference Efficient Vision Transformers
We show that such models can be vulnerable to a universal adversarial patch attack, where the attacker optimizes for a patch that when pasted on any image, can increase the compute and power consumption of the model.
A Cookbook of Self-Supervised Learning
Self-supervised learning, dubbed the dark matter of intelligence, is a promising path to advance machine learning.
Defending Against Patch-based Backdoor Attacks on Self-Supervised Learning
It was shown that an adversary can poison a small part of the unlabeled data so that when a victim trains an SSL model on it, the final model will have a backdoor that the adversary can exploit.
Is Multi-Task Learning an Upper Bound for Continual Learning?
Moreover, it is imaginable that when learning from multiple tasks, a small subset of these tasks could behave as adversarial tasks reducing the overall learning performance in a multi-task setting.
SimA: Simple Softmax-free Attention for Vision Transformers
Recently, vision transformers have become very popular.
Backdoor Attacks on Vision Transformers
Vision Transformers (ViT) have recently demonstrated exemplary performance on a variety of vision tasks and are being used as an alternative to CNNs.
PRANC: Pseudo RAndom Networks for Compacting deep models
We demonstrate that a deep model can be reparametrized as a linear combination of several randomly initialized and frozen deep models in the weight space.
A Simple Approach to Adversarial Robustness in Few-shot Image Classification
Few-shot image classification, where the goal is to generalize to tasks with limited labeled data, has seen great progress over the years.
Sparsity and Heterogeneous Dropout for Continual Learning in the Null Space of Neural Activations
Overcoming catastrophic forgetting in deep neural networks has become an active field of research in recent years.
Amenable Sparse Network Investigator
ASNI-II learns a sparse network and an initialization that is quantized, compressed, and from which the sparse network is trainable.
SimReg: Regression as a Simple Yet Effective Tool for Self-supervised Knowledge Distillation
Feature regression is a simple way to distill large neural network models to smaller ones.
A Fistful of Words: Learning Transferable Visual Models from Bag-of-Words Supervision
In this paper, we focus on teasing out what parts of the language supervision are essential for training zero-shot image classification models.
MASTAF: A Model-Agnostic Spatio-Temporal Attention Fusion Network for Few-shot Video Classification
We propose MASTAF, a Model-Agnostic Spatio-Temporal Attention Fusion network for few-shot video classification.
Constrained Mean Shift Using Distant Yet Related Neighbors for Representation Learning
On the other hand, far away NNs may not be semantically related to the query.
Adaptive Token Sampling For Efficient Vision Transformers
Since ATS is a parameter-free module, it can be added to the off-the-shelf pre-trained vision transformers as a plug and play module, thus reducing their GFLOPs without any additional training.
Ranked #13 on
Efficient ViTs
on ImageNet-1K (with DeiT-S)
A Simple Baseline for Low-Budget Active Learning
However, most such methods assume that a large subset of the data can be annotated.
Constrained Mean Shift for Representation Learning
Inspired by recent success of self-supervised learning (SSL), we develop a non-contrastive representation learning method that can exploit additional knowledge.
Consistent Explanations by Contrastive Learning
We show that our method, Contrastive Grad-CAM Consistency (CGC), results in Grad-CAM interpretation heatmaps that are more consistent with human annotations while still achieving comparable classification accuracy.
Backdoor Attacks on Self-Supervised Learning
We show that such methods are vulnerable to backdoor attacks - where an attacker poisons a small part of the unlabeled data by adding a trigger (image patch chosen by the attacker) to the images.
Mean Shift for Self-Supervised Learning
Most recent self-supervised learning (SSL) algorithms learn features by contrasting between instances of images or by clustering the images and then contrasting between the image clusters.
ISD: Self-Supervised Learning by Iterative Similarity Distillation
Hence, we introduce a self supervised learning algorithm where we use a soft similarity for the negative images rather than a binary distinction between positive and negative pairs.
COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning
Many real-world video-text tasks involve different levels of granularity, such as frames and words, clip and sentences or videos and paragraphs, each with distinct semantics.
Ranked #4 on
Video Captioning
on ActivityNet Captions
CompRess: Self-Supervised Learning by Compressing Representations
To the best of our knowledge, this is the first time a self-supervised AlexNet has outperformed supervised one on ImageNet classification.
A simple baseline for domain adaptation using rotation prediction
We show that removing this bias from the unlabeled data results in a large drop in performance of state-of-the-art methods, while our simple method is relatively robust.
Hidden Trigger Backdoor Attacks
Backdoor attacks are a form of adversarial attacks on deep networks where the attacker provides poisoned data to the victim to train the model with, and then activates the attack by showing a specific small trigger pattern at the test time.
Role of Spatial Context in Adversarial Robustness for Object Detection
However, one can show that an adversary can design adversarial patches which do not overlap with any objects of interest in the scene and exploit contextual reasoning to fool standard detectors.
Universal Litmus Patterns: Revealing Backdoor Attacks in CNNs
In this paper, we introduce a benchmark technique for detecting backdoor attacks (aka Trojan attacks) on deep convolutional neural networks (CNNs).
Fooling Network Interpretation in Image Classification
Deep neural networks have been shown to be fooled rather easily using adversarial attack algorithms.
Boosting Self-Supervised Learning via Knowledge Transfer
We use this framework to design a novel self-supervised task, which achieves state-of-the-art performance on the common benchmarks in PASCAL VOC 2007, ILSVRC12 and Places by a significant margin.
Representation Learning by Learning to Count
In this paper, we use two image transformations in the context of counting: scaling and tiling.
Weakly Supervised Cascaded Convolutional Networks
The final stage of both architectures is a part of a convolutional neural network that performs multiple instance learning on proposals extracted in the previous stage(s).
Ranked #2 on
Weakly Supervised Object Detection
on ImageNet
Cross-Modal Scene Networks
Our experiments suggest that our scene representation can help transfer representations across modalities for retrieval.
Generating Videos with Scene Dynamics
We capitalize on large amounts of unlabeled video in order to learn a model of scene dynamics for both video recognition tasks (e. g. action classification) and video generation tasks (e. g. future prediction).
DeepCAMP: Deep Convolutional Action & Attribute Mid-Level Patterns
On the other hand, we let an iteration of feature learning and patch clustering purify the set of dedicated patches that we use.
Learning Aligned Cross-Modal Representations from Weakly Aligned Data
Our experiments suggest that our scene representation can help transfer representations across modalities for retrieval.
Joint Semantic Segmentation and Depth Estimation with Deep Convolutional Networks
The proposed model is trained and evaluated on NYUDepth V2 dataset outperforming the state of the art methods on semantic segmentation and achieving comparable results on the task of depth estimation.
Anticipating Visual Representations from Unlabeled Video
The key idea behind our approach is that we can train deep networks to predict the visual representation of images in the future.
Visualizing Object Detection Features
We introduce algorithms to visualize feature spaces used by object detectors.
Learning visual biases from human imagination
Although the human visual system can recognize many concepts under challenging conditions, it still has some biases.
Predicting Motivations of Actions by Leveraging Text
In this paper, we introduce the problem of predicting why a person has performed an action in images.
Parsing Videos of Actions with Segmental Grammars
Real-world videos of human activities exhibit temporal structure at various scales; long videos are typically composed out of multiple action instances, where each instance is itself composed of sub-actions with variable durations and orderings.
Are all training examples equally valuable?
When learning a new concept, not all training examples may prove equally useful for training: some may have higher or lower training value than others.
Bilinear classifiers for visual recognition
Bilinear classifiers are a discriminative variant of bilinear models, which capture the dependence of data on multiple factors.
