Related papers: MDS-DETR: DETR with Masked Duplicate Suppressor

Compared to monocular 3D object detection, stereo-based 3D methods offer significantly higher accuracy but still suffer from high computational overhead and latency. The state-of-the-art stereo 3D detection method achieves twice the…

Tiny object detection plays a vital role in drone surveillance, remote sensing, and autonomous systems, enabling the identification of small targets across vast landscapes. However, existing methods suffer from inefficient feature leverage…

Object detection is an important topic in computer vision, with post-processing, an essential part of the typical object detection pipeline, posing a significant bottleneck affecting the performance of traditional object detection models.…

Contrastive learning methods in self-supervised settings have primarily focused on pre-training encoders, while decoders are typically introduced and trained separately for downstream dense prediction tasks. However, this conventional…

Despite the promising results, existing oriented object detection methods usually involve heuristically designed rules, e.g., RRoI generation, rotated NMS. In this paper, we propose an end-to-end framework for oriented object detection,…

Numerous dual-energy CT (DECT) techniques have been developed in the past few decades. Dual-energy CT (DECT) statistical iterative reconstruction (SIR) has demonstrated its potential for reducing noise and increasing accuracy. Our lab…

Small Object Detection (SOD) poses significant challenges due to limited information and the model's low class prediction score. While Transformer-based detectors have shown promising performance, their potential for SOD remains largely…

Transformers have revolutionized the object detection landscape by introducing DETRs, acclaimed for their simplicity and efficacy. Despite their advantages, the substantial size of these models poses significant challenges for practical…

Modern language models (LMs) are trained in an autoregressive manner, conditioned only on the prefix. In contrast, sequence labeling (SL) tasks assign labels to each individual input token, naturally benefiting from bidirectional context.…

Detection Transformers (DETR) are renowned object detection pipelines, however computationally efficient multiscale detection using DETR is still challenging. In this paper, we propose a Cross-Resolution Encoding-Decoding (CRED) mechanism…

The introduction of DETR represents a new paradigm for object detection. However, its decoder conducts classification and box localization using shared queries and cross-attention layers, leading to suboptimal results. We observe that…

DETR is the first fully end-to-end detector that predicts a final set of predictions without post-processing. However, it suffers from problems such as low performance and slow convergence. A series of works aim to tackle these issues in…

Modern detection transformers (DETRs) use a set of object queries to predict a list of bounding boxes, sort them by their classification confidence scores, and select the top-ranked predictions as the final detection results for the given…

DEtection TRansformer (DETR) becomes a dominant paradigm, mainly due to its common architecture with high accuracy and no post-processing. However, DETR suffers from unstable training dynamics. It consumes more data and epochs to converge…

Unsupervised multivariate time series (MTS) representation learning aims to extract compact and informative representations from raw sequences without relying on labels, enabling efficient transfer to diverse downstream tasks. In this…

We propose a dynamic encoder transducer (DET) for on-device speech recognition. One DET model scales to multiple devices with different computation capacities without retraining or finetuning. To trading off accuracy and latency, DET…

While various knowledge distillation (KD) methods in CNN-based detectors show their effectiveness in improving small students, the baselines and recipes for DETR-based detectors are yet to be built. In this paper, we focus on the…

Masked diffusion language models (MDLMs) have recently emerged as a promising alternative to autoregressive (AR) language models, offering properties such as parallel decoding, flexible generation orders, and the potential for fewer…

We present a mask-piloted Transformer which improves masked-attention in Mask2Former for image segmentation. The improvement is based on our observation that Mask2Former suffers from inconsistent mask predictions between consecutive decoder…

Deep prompt tuning (DPT) has gained great success in most natural language processing~(NLP) tasks. However, it is not well-investigated in dense retrieval where fine-tuning~(FT) still dominates. When deploying multiple retrieval tasks using…