Search Results for author:
Found 23 papers, 8 papers with code
How Does BERT Rerank Passages? An Attribution Analysis with Information Bottlenecks
Fine-tuned pre-trained transformers achieve the state of the art in passage reranking.
Towards Robust Image Stitching: An Adaptive Resistance Learning against Compatible Attacks
Given a pair of captured images, subtle perturbations and distortions which go unnoticed by the human visual system tend to attack the correspondence matching, impairing the performance of image stitching algorithms.
From Text to Pixels: A Context-Aware Semantic Synergy Solution for Infrared and Visible Image Fusion
With the rapid progression of deep learning technologies, multi-modality image fusion has become increasingly prevalent in object detection tasks.
Holistic Dynamic Frequency Transformer for Image Fusion and Exposure Correction
The correction of exposure-related issues is a pivotal component in enhancing the quality of images, offering substantial implications for various computer vision tasks.
Fearless Luminance Adaptation: A Macro-Micro-Hierarchical Transformer for Exposure Correction
To overcome these limitations, we propose a Macro-Micro-Hierarchical transformer, which consists of a macro attention to capture long-range dependencies, a micro attention to extract local features, and a hierarchical structure for coarse-to-fine correction.
Approximating Human-Like Few-shot Learning with GPT-based Compression
Leveraging the approximated information distance, our method allows the direct application of GPT models in quantitative text similarity measurements.
WaterFlow: Heuristic Normalizing Flow for Underwater Image Enhancement and Beyond
Underwater images suffer from light refraction and absorption, which impairs visibility and interferes the subsequent applications.
Multi-Spectral Image Stitching via Spatial Graph Reasoning
Multi-spectral image stitching leverages the complementarity between infrared and visible images to generate a robust and reliable wide field-of-view (FOV) scene.
Contrastive Learning Based Recursive Dynamic Multi-Scale Network for Image Deraining
Extensive experiments on synthetic benchmarks and real-world images demonstrate that the proposed RDMC delivers strong performance on the depiction of rain streaks and outperforms the state-of-the-art methods.
Breaking Modality Disparity: Harmonized Representation for Infrared and Visible Image Registration
Since the differences in viewing range, resolution and relative position, the multi-modality sensing module composed of infrared and visible cameras needs to be registered so as to have more accurate scene perception.
A Theory of Human-Like Few-Shot Learning
We aim to bridge the gap between our common-sense few-sample human learning and large-data machine learning.
Less is More: Parameter-Free Text Classification with Gzip
Our method also performs particularly well in few-shot settings where labeled data are too scarce for DNNs to achieve a satisfying accuracy.
What the DAAM: Interpreting Stable Diffusion Using Cross Attention
Large-scale diffusion neural networks represent a substantial milestone in text-to-image generation, but they remain poorly understood, lacking interpretability analyses.
Building an Efficiency Pipeline: Commutativity and Cumulativeness of Efficiency Operators for Transformers
There exists a wide variety of efficiency methods for natural language processing (NLP) tasks, such as pruning, distillation, dynamic inference, quantization, etc.
Few-Shot Non-Parametric Learning with Deep Latent Variable Model
Most real-world problems that machine learning algorithms are expected to solve face the situation with 1) unknown data distribution; 2) little domain-specific knowledge; and 3) datasets with limited annotation.
Investigating the Limitations of Transformers with Simple Arithmetic Tasks
In this work, we investigate if the surface form of a number has any influence on how sequence-to-sequence language models learn simple arithmetic tasks such as addition and subtraction across a wide range of values.
Inserting Information Bottlenecks for Attribution in Transformers
We show the effectiveness of our method in terms of attribution and the ability to provide insight into how information flows through layers.
Document Ranking with a Pretrained Sequence-to-Sequence Model
We investigate this observation further by varying target words to probe the model's use of latent knowledge.
Ranked #1 on
Ad-Hoc Information Retrieval
on TREC Robust04
Navigation-Based Candidate Expansion and Pretrained Language Models for Citation Recommendation
Citation recommendation systems for the scientific literature, to help authors find papers that should be cited, have the potential to speed up discoveries and uncover new routes for scientific exploration.
PaperRobot: Incremental Draft Generation of Scientific Ideas
We present a PaperRobot who performs as an automatic research assistant by (1) conducting deep understanding of a large collection of human-written papers in a target domain and constructing comprehensive background knowledge graphs (KGs); (2) creating new ideas by predicting links from the background KGs, by combining graph attention and contextual text attention; (3) incrementally writing some key elements of a new paper based on memory-attention networks: from the input title along with predicted related entities to generate a paper abstract, from the abstract to generate conclusion and future work, and finally from future work to generate a title for a follow-on paper.
Describing a Knowledge Base
We aim to automatically generate natural language descriptions about an input structured knowledge base (KB).
Chengyu Cloze Test
We present a neural recommendation model for Chengyu, which is a special type of Chinese idiom.
Learning Aggregated Transmission Propagation Networks for Haze Removal and Beyond
However, they may fail when their assumptions are not valid on specific images.
