Related papers: The MixCount Dataset: Bridging the Data Gap for Op…

Dataset pruning -- selecting a small yet informative subset of training data -- has emerged as a promising strategy for efficient machine learning, offering significant reductions in computational cost and storage compared to alternatives…

Image captioning requires numerous annotated image-text pairs, resulting in substantial annotation costs. Recently, large models (e.g. diffusion models and large language models) have excelled in producing high-quality images and text. This…

Mixture of Experts (MoE) models based on Transformer architecture are pushing the boundaries of language and vision tasks. The allure of these models lies in their ability to substantially increase the parameter count without a…

Label-efficient LiDAR-based 3D object detection is currently dominated by weakly/semi-supervised methods. Instead of exclusively following one of them, we propose MixSup, a more practical paradigm simultaneously utilizing massive cheap…

A fundamental problem in robotic perception is matching identical objects or data, with applications such as loop closure detection, place recognition, object tracking, and map fusion. While the problem becomes considerably more challenging…

Object counting and localization are key steps for quantitative analysis in large-scale microscopy applications. This procedure becomes challenging when target objects are overlapping, are densely clustered, and/or present fuzzy boundaries.…

Unsupervised object-centric learning methods allow the partitioning of scenes into entities without additional localization information and are excellent candidates for reducing the annotation burden of multiple-object tracking (MOT)…

Mixture-of-Experts (MoE) models have shown remarkable capability in instruction tuning, especially when the number of tasks scales. However, previous methods simply merge all training tasks (e.g. creative writing, coding, and mathematics)…

Scale variation across object instances remains a key challenge in object detection task. Despite the remarkable progress made by modern detection models, this challenge is particularly evident in the semi-supervised case. While existing…

Data mixing augmentation have proved to be effective in improving the generalization ability of deep neural networks. While early methods mix samples by hand-crafted policies (e.g., linear interpolation), recent methods utilize saliency…

Object counting, whose aim is to estimate the number of objects from a given image, is an important and challenging computation task. Significant efforts have been devoted to addressing this problem and achieved great progress, yet counting…

Building rich machine learning datasets in a scalable manner often necessitates a crowd-sourced data collection pipeline. In this work, we use human studies to investigate the consequences of employing such a pipeline, focusing on the…

Point cloud-based open-vocabulary 3D object detection aims to detect 3D categories that do not have ground-truth annotations in the training set. It is extremely challenging because of the limited data and annotations (bounding boxes with…

Machine learning models tend to over-rely on statistical shortcuts. These spurious correlations between parts of the input and the output labels does not hold in real-world settings. We target this issue on the recent open-ended visual…

Object counting has achieved remarkable success on visible instances, yet state-of-the-art (SOTA) methods fail under occlusion. This failure stems from a fundamental architectural limitation where backbone networks encode occluding surfaces…

Object detectors are typically learned on fully-annotated training data with fixed predefined categories. However, categories are often required to be increased progressively. Usually, only the original training set annotated with old…

Semi-supervised learning has proven to be a powerful paradigm for leveraging unlabeled data to mitigate the reliance on large labeled datasets. In this work, we unify the current dominant approaches for semi-supervised learning to produce a…

The growing scale of datasets in deep learning has introduced significant computational challenges. Dataset pruning addresses this challenge by constructing a compact but informative coreset from the full dataset with comparable…

This paper studies the training-testing discrepancy (a.k.a. exposure bias) problem for improving the diffusion models. During training, the input of a prediction network at one training timestep is the corresponding ground-truth noisy data…

This paper presents CountEx, a discriminative visual counting framework designed to address a key limitation of existing prompt-based methods: the inability to explicitly exclude visually similar distractors. While current approaches allow…