相关论文: Filtering, Distillation, and Hard Negatives for Vi…

Negative sampling is a limiting factor w.r.t. the generalization of metric-learned neural networks. We show that uniform negative sampling provides little information about the class boundaries and thus propose three novel techniques for…

Learning representations of images that are invariant to sensitive or unwanted attributes is important for many tasks including bias removal and cross domain retrieval. Here, our objective is to learn representations that are invariant to…

Commit Classification (CC) is an important task in software maintenance, which helps software developers classify code changes into different types according to their nature and purpose. It allows developers to understand better how their…

When considering post-training quantization, prior work has typically focused on developing a mixed precision scheme or learning the best way to partition a network for quantization. In our work, CPT-V, we look at a general way to improve…

Contrastive Language-Image Pre-training (CLIP) on large-scale image-caption datasets learns representations that can achieve remarkable zero-shot generalization. However, such models require a massive amount of pre-training data. Improving…

Most dataset distillation methods struggle to accommodate large-scale datasets due to their substantial computational and memory requirements. Recent research has begun to explore scalable disentanglement methods. However, there are still…

Deep learning has achieved outstanding performance for face recognition benchmarks, but performance reduces significantly for low resolution (LR) images. We propose an attention similarity knowledge distillation approach, which transfers…

Humans use abstract concepts for understanding instead of hard features. Recent interpretability research has focused on human-centered concept explanations of neural networks. Concept Activation Vectors (CAVs) estimate a model's…

Recently, many zero-shot learning (ZSL) methods focused on learning discriminative object features in an embedding feature space, however, the distributions of the unseen-class features learned by these methods are prone to be partly…

Contrastive language-image pretraining has shown great success in learning visual-textual joint representation from web-scale data, demonstrating remarkable "zero-shot" generalization ability for various image tasks. However, how to…

Vision-Language Models (VLMs) demonstrate remarkable zero-shot generalization to unseen tasks, but fall short of the performance of supervised methods in generalizing to downstream tasks with limited data. Prompt learning is emerging as a…

The conventional few-shot classification aims at learning a model on a large labeled base dataset and rapidly adapting to a target dataset that is from the same distribution as the base dataset. However, in practice, the base and the target…

Recently, representation learning with contrastive learning algorithms has been successfully applied to challenging unlabeled datasets. However, these methods are unable to distinguish important features from unimportant ones under simply…

Distillation from Weak Teacher (DWT) is a method of transferring knowledge from a smaller, weaker teacher model to a larger student model to improve its performance. Previous studies have shown that DWT can be effective in the vision domain…

Dataset distillation (DD) compresses a large training set into a small synthetic set for efficient training, but most DD methods optimize only clean accuracy and leave robustness uncontrolled. Recent robust DD methods improve robustness,…

Recent developments in natural language representations have been accompanied by large and expensive models that leverage vast amounts of general-domain text through self-supervised pre-training. Due to the cost of applying such models to…

Model agnostic meta-learning algorithms aim to infer priors from several observed tasks that can then be used to adapt to a new task with few examples. Given the inherent diversity of tasks arising in existing benchmarks, recent methods use…

We address the problem of few-shot semantic segmentation (FSS), which aims to segment novel class objects in a target image with a few annotated samples. Though recent advances have been made by incorporating prototype-based metric…

Finetuning image-text models such as CLIP achieves state-of-the-art accuracies on a variety of benchmarks. However, recent works like WiseFT (Wortsman et al., 2021) and LP-FT (Kumar et al., 2022) have shown that even subtle differences in…

Collecting labeled data for the task of semantic segmentation is expensive and time-consuming, as it requires dense pixel-level annotations. While recent Convolutional Neural Network (CNN) based semantic segmentation approaches have…