Related papers: The Devil is in Fine-tuning and Long-tailed Proble…

Sequence labeling (SL) is a fundamental research problem encompassing a variety of tasks, e.g., part-of-speech (POS) tagging, named entity recognition (NER), text chunking, etc. Though prevalent and effective in many downstream applications…

Scene text detection and document layout analysis have long been treated as two separate tasks in different image domains. In this paper, we bring them together and introduce the task of unified scene text detection and layout analysis. The…

Dataset distillation creates a small distilled set that enables efficient training by capturing key information from the full dataset. While existing dataset distillation methods perform well on balanced datasets, they struggle under…

Instance segmentation has witnessed a remarkable progress on class-balanced benchmarks. However, they fail to perform as accurately in real-world scenarios, where the category distribution of objects naturally comes with a long tail.…

Extreme multi-label text classification (XMTC) refers to the problem of tagging a given text with the most relevant subset of labels from a large label set. A majority of labels only have a few training instances due to large label…

Motivation: Despite recent advancements in semantic representation driven by pre-trained and large-scale language models, addressing long tail challenges in multi-label text classification remains a significant issue. Long tail challenges…

Camera-only 3D object detection has emerged as a cost-effective and scalable alternative to LiDAR for autonomous driving, yet existing methods primarily prioritize overall performance while overlooking the severe long-tail imbalance…

Scene labeling is a challenging classification problem where each input image requires a pixel-level prediction map. Recently, deep-learning-based methods have shown their effectiveness on solving this problem. However, we argue that the…

The world is long-tailed. What does this mean for computer vision and visual recognition? The main two implications are (1) the number of categories we need to consider in applications can be very large, and (2) the number of training…

Safety tuning through supervised fine-tuning and reinforcement learning from human feedback has substantially improved the robustness of large language models (LLMs). However, it often suppresses rather than eliminates unsafe behaviors,…

Long-tailed multi-label visual recognition poses a significant challenge, as images typically contain multiple labels with highly imbalanced class distributions, leading to biased models that favor head classes while underperforming on tail…

To combat the misuse of Large Language Models (LLMs), many recent studies have presented LLM-generated-text detectors with promising performance. When users instruct LLMs to generate texts, the instruction can include different constraints…

Offline handwritten text recognition from images is an important problem for enterprises attempting to digitize large volumes of handmarked scanned documents/reports. Deep recurrent models such as Multi-dimensional LSTMs have been shown to…

Detecting evidence within the context is a key step in the process of reasoning task. Evaluating and enhancing the capabilities of LLMs in evidence detection will strengthen context-based reasoning performance. This paper proposes a…

Scene text retrieval aims to localize and search all text instances from an image gallery, which are the same or similar to a given query text. Such a task is usually realized by matching a query text to the recognized words, outputted by…

Going beyond mere fine-tuning of vision-language models (VLMs), learnable prompt tuning has emerged as a promising, resource-efficient alternative. Despite their potential, effectively learning prompts faces the following challenges: (i)…

Recently, large-scale visual language pre-trained (VLP) models have demonstrated impressive performance across various downstream tasks. Motivated by these advancements, pioneering efforts have emerged in multi-label image recognition with…

The current studies of Scene Graph Generation (SGG) focus on solving the long-tailed problem for generating unbiased scene graphs. However, most de-biasing methods overemphasize the tail predicates and underestimate head ones throughout…

Despite the huge progress in scene graph generation in recent years, its long-tail distribution in object relationships remains a challenging and pestering issue. Existing methods largely rely on either external knowledge or statistical…

Multi-label classification problems with thousands of classes are hard to solve with in-context learning alone, as language models (LMs) might lack prior knowledge about the precise classes or how to assign them, and it is generally…