In MVIT, why does the accuracy drop significantly after I add the DETECTION.ENABLE: TRUE option?

This is my config file：MVITv2_S_16x4.yaml

TRAIN:
ENABLE: False
DATASET: kinetics
BATCH_SIZE: 16
EVAL_PERIOD: 10
CHECKPOINT_PERIOD: 10
CHECKPOINT_FILE_PATH: "/home/sakai/data/sourcecode/py/mvit-v2/demo/Kinetics/MViTv2_S_16x4_k400_f302660347.pyth"
AUTO_RESUME: True
DATA:
USE_OFFSET_SAMPLING: True
DECODING_BACKEND: torchvision
NUM_FRAMES: 16
SAMPLING_RATE: 4
TRAIN_JITTER_SCALES: [256, 320]
TRAIN_CROP_SIZE: 224
TEST_CROP_SIZE: 224
INPUT_CHANNEL_NUM: [3]
TRAIN_JITTER_SCALES_RELATIVE: [0.08, 1.0]
TRAIN_JITTER_ASPECT_RELATIVE: [0.75, 1.3333]
MVIT:
ZERO_DECAY_POS_CLS: False
USE_ABS_POS: False
REL_POS_SPATIAL: True
REL_POS_TEMPORAL: True
DEPTH: 16
NUM_HEADS: 1
EMBED_DIM: 96
PATCH_KERNEL: (3, 7, 7)
PATCH_STRIDE: (2, 4, 4)
PATCH_PADDING: (1, 3, 3)
MLP_RATIO: 4.0
QKV_BIAS: True
DROPPATH_RATE: 0.2
NORM: "layernorm"
MODE: "conv"
CLS_EMBED_ON: True
DIM_MUL: [[1, 2.0], [3, 2.0], [14, 2.0]]
HEAD_MUL: [[1, 2.0], [3, 2.0], [14, 2.0]]
POOL_KVQ_KERNEL: [3, 3, 3]
POOL_KV_STRIDE_ADAPTIVE: [1, 8, 8]
POOL_Q_STRIDE: [[0, 1, 1, 1], [1, 1, 2, 2], [2, 1, 1, 1], [3, 1, 2, 2], [4, 1, 1, 1], [5, 1, 1, 1], [6, 1, 1, 1], [7, 1, 1, 1], [8, 1, 1, 1], [9, 1, 1, 1], [10, 1, 1, 1], [11, 1, 1, 1], [12, 1, 1, 1], [13, 1, 1, 1], [14, 1, 2, 2], [15, 1, 1, 1]]
DROPOUT_RATE: 0.0
DIM_MUL_IN_ATT: True
RESIDUAL_POOLING: True
AUG:
NUM_SAMPLE: 2
ENABLE: True
COLOR_JITTER: 0.4
AA_TYPE: rand-m7-n4-mstd0.5-inc1
INTERPOLATION: bicubic
RE_PROB: 0.25
RE_MODE: pixel
RE_COUNT: 1
RE_SPLIT: False
MIXUP:
ENABLE: True
ALPHA: 0.8
CUTMIX_ALPHA: 1.0
PROB: 1.0
SWITCH_PROB: 0.5
LABEL_SMOOTH_VALUE: 0.1
SOLVER:
ZERO_WD_1D_PARAM: True
BASE_LR_SCALE_NUM_SHARDS: True
CLIP_GRAD_L2NORM: 1.0
BASE_LR: 0.0001
COSINE_AFTER_WARMUP: True
COSINE_END_LR: 1e-6
WARMUP_START_LR: 1e-6
WARMUP_EPOCHS: 30.0
LR_POLICY: cosine
MAX_EPOCH: 200
MOMENTUM: 0.9
WEIGHT_DECAY: 0.05
OPTIMIZING_METHOD: adamw
COSINE_AFTER_WARMUP: True
MODEL:
NUM_CLASSES: 400
ARCH: mvit
MODEL_NAME: MViT
LOSS_FUNC: soft_cross_entropy
DROPOUT_RATE: 0.5
TEST:
ENABLE: False
DATASET: kinetics
BATCH_SIZE: 64
NUM_SPATIAL_CROPS: 1
NUM_ENSEMBLE_VIEWS: 5
DATA_LOADER:
NUM_WORKERS: 8
PIN_MEMORY: True
NUM_GPUS: 1
NUM_SHARDS: 1
RNG_SEED: 0
OUTPUT_DIR: .
DETECTION:
ENABLE: True

DEMO:
ENABLE: True
VIS_MODE: "top-k"
THREAD_ENABLE: False
LABEL_FILE_PATH: "/home/sakai/data/sourcecode/py/mvit-v2/demo/Kinetics/kinetics_classnames.json" # Add local label file path here.
OUTPUT_FILE:
INPUT_VIDEO:
DETECTRON2_CFG: "COCO-Detection/faster_rcnn_R_50_FPN_3x.yaml"
DETECTRON2_WEIGHTS: detectron2://COCO-Detection/faster_rcnn_R_50_FPN_3x/137849458/model_final_280758.pkl

this is the demo