相关论文: LibraGrad: Balancing Gradient Flow for Universally…

Gradient-based saliency methods are widely used to interpret deep neural networks, yet they often produce noisy and unstable explanations that poorly align with semantically meaningful input features. We argue that a fundamental cause of…

A well-designed fine-grained categorization system usually has three contradictory requirements: accuracy (the ability to identify objects among subordinate categories); interpretability (the ability to provide human-understandable…

Human-aligned deep learning models exhibit behaviors consistent with human values, such as robustness, fairness, and honesty. Transferring these behavioral properties to models trained on different tasks or data distributions remains…

Semantic grids can be useful representations of the scene around an autonomous system. By having information about the layout of the space around itself, a robot can leverage this type of representation for crucial tasks such as navigation…

Deep networks have shown remarkable performance across a wide range of tasks, yet getting a global concept-level understanding of how they function remains a key challenge. Many post-hoc concept-based approaches have been introduced to…

How can we accurately classify graphs? Graph classification is a pivotal task in data mining with applications in social network analysis, web analysis, drug discovery, molecular property prediction, etc. Graph neural networks have achieved…

A challenge in advancing Visual-Language Models (VLMs) is determining whether their failures on abstract reasoning tasks, such as Bongard problems, stem from flawed perception or faulty top-down reasoning. To disentangle these factors, we…

Fine-tuning pretrained self-supervised language models is widely adopted for transfer learning to downstream tasks. Fine-tuning can be achieved by freezing gradients of the pretrained network and only updating gradients of a newly added…

Instruction tuning is one of the key steps required for adapting large language models (LLMs) to a broad spectrum of downstream applications. However, this procedure is difficult because real-world datasets are rarely homogeneous; they…

TextGrad is a novel approach to text-based automatic differentiation that enables composite AI systems to perform optimization without explicit numerical equations. However, it currently lacks self-verification mechanisms that ensure…

Adapting vision-language models (VLMs) to downstream tasks with pseudolabels has gained increasing attention. A major obstacle is that the pseudolabels generated by VLMs tend to be imbalanced, leading to inferior performance. While existing…

Most popular optimizers for deep learning can be broadly categorized as adaptive methods (e.g. Adam) and accelerated schemes (e.g. stochastic gradient descent (SGD) with momentum). For many models such as convolutional neural networks…

Multitask learning is being increasingly adopted in applications domains like computer vision and reinforcement learning. However, optimally exploiting its advantages remains a major challenge due to the effect of negative transfer.…

Estimating the complete 3D point cloud from an incomplete one is a key problem in many vision and robotics applications. Mainstream methods (e.g., PCN and TopNet) use Multi-layer Perceptrons (MLPs) to directly process point clouds, which…

Compared with model architectures, the training process, which is also crucial to the success of detectors, has received relatively less attention in object detection. In this work, we carefully revisit the standard training practice of…

The gradient-weighted class activation mapping (Grad-CAM) method can faithfully highlight important regions in images for deep model prediction in image classification, image captioning and many other tasks. It uses the gradients in…

Accurately understanding the intent behind speech, conversation, and writing is crucial to the development of helpful Large Language Model (LLM) assistants. This paper introduces IntentGrasp, a comprehensive benchmark for evaluating the…

Gradient regularization (GR) is a method that penalizes the gradient norm of the training loss during training. While some studies have reported that GR can improve generalization performance, little attention has been paid to it from the…

Classifiers often learn to be biased corresponding to the class-imbalanced dataset, especially under the semi-supervised learning (SSL) set. While previous work tries to appropriately re-balance the classifiers by subtracting a…

Vision-language models (VLMs), such as CLIP, have demonstrated exceptional generalization capabilities and can quickly adapt to downstream tasks through prompt fine-tuning. Unfortunately, in classification tasks involving non-training…