Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

NesT

Computer VisionIntroduced 200037 papers

Description

NesT stacks canonical transformer layers to conduct local self-attention on every image block independently, and then "nests" them hierarchically. Coupling of processed information between spatially adjacent blocks is achieved through a proposed block aggregation between every two hierarchies. The overall hierarchical structure can be determined by two key hyper-parameters: patch size $S × S$ and number of block hierarchies $T_d$ . All blocks inside each hierarchy share one set of parameters. Given input of image, each image is linearly projected to an embedding. All embeddings are partitioned to blocks and flattened to generate final input. Each transformer layers is composed of a multi-head self attention (MSA) layer followed by a feed-forward fully-connected network (FFN) with skip-connection and Layer normalization. Positional embeddings are added to encode spatial information before feeding into the block. Lastly, a nested hierarchy with block aggregation is built -- every four spatially connected blocks are merged into one.

Papers Using This Method

NestQuant: Post-Training Integer-Nesting Quantization for On-Device DNN2025-06-22 Mixed-feedback oscillations in the foraging dynamics of arboreal turtle ants2025-04-15 Experimental Validation of Distributed Dispatching of Multiple Active Distribution Networks Using the ADMM2025-03-19 NEST: A Neuromodulated Small-world Hypergraph Trajectory Prediction Model for Autonomous Driving2024-12-16 Ant Nest Detection Using Underground P-Band TomoSAR2024-12-16 Argentine ants regulate traffic flow with stopped individuals2024-12-09 Revisiting the Many Instruments Problem using Random Matrix Theory2024-08-16 Performance Prediction of Hub-Based Swarms2024-08-09 Soli-enabled Noncontact Heart Rate Detection for Sleep and Meditation Tracking2024-07-08 NeST: Neural Stress Tensor Tomography by leveraging 3D Photoelasticity2024-06-14 Nearest Neighbor Speculative Decoding for LLM Generation and Attribution2024-05-29 Direct learning of home vector direction for insect-inspired robot navigation2024-05-06 LOOPer: A Learned Automatic Code Optimizer For Polyhedral Compilers2024-03-18 DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers2024-02-25 Norm Enforcement with a Soft Touch: Faster Emergence, Happier Agents2024-01-29 Timing decisions as the next frontier for collective intelligence2023-12-01 InsPLAD: A Dataset and Benchmark for Power Line Asset Inspection in UAV Images2023-11-02 Robustify and Tighten the Lee Bounds: A Sample Selection Model under Stochastic Monotonicity and Symmetry Assumptions2023-11-01 Interpreting TSLS Estimators in Information Provision Experiments2023-09-09 Finite population effects on optimal communication for social foragers2023-08-01